Unsupervised Decomposition Methods for Analysis of Multimodal Neural Data

Felix Biessmann, Frank C. Meinecke, Klaus Muller

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

Technical advances in the field of noninvasive neuroimaging allow for innovative therapeutical strategies with application potential in neural rehabilitation. To improve these methods, combinations of multiple imaging modalities have become an important topic of research. This chapter reviews some of the most popular unsupervised statistical learning techniques used in the context of neuroscientific data analysis, and places a special focus on multimodal neural data. It starts with the well-known principal component analysis (PCA). First, the chapter shows how to derive the algorithm and provides illustrative examples of the advantages and disadvantages of standard PCA. The second method presented is canonical correlation analysis (CCA): a multivariate analysis method that reveals maximally correlated features of simultaneously acquired multiple data streams. Finally the chapter presents a straightforward extension of CCA that estimates the correct solution even in the presence of noninstantaneous couplings, that is, temporal delays or convolutions between data sources.

Original languageEnglish
Title of host publicationIntroduction to Neural Engineering for Motor Rehabilitation
Publisherwiley
Pages199-234
Number of pages36
ISBN (Electronic)9781118628522
ISBN (Print)9780470916735
DOIs
Publication statusPublished - 2013 Jul 15
Externally publishedYes

Fingerprint

Principal component analysis
Neuroimaging
Principal Component Analysis
Decomposition
Convolution
Patient rehabilitation
Information Storage and Retrieval
Imaging techniques
Rehabilitation
Multivariate Analysis
Learning
Research

Keywords

  • Canonical correlation analysis (CCA)
  • Multimodal neural data
  • Noninvasive neuroimaging
  • Principal component analysis (PCA)

ASJC Scopus subject areas

  • Biochemistry, Genetics and Molecular Biology(all)

Cite this

Biessmann, F., Meinecke, F. C., & Muller, K. (2013). Unsupervised Decomposition Methods for Analysis of Multimodal Neural Data. In Introduction to Neural Engineering for Motor Rehabilitation (pp. 199-234). wiley. https://doi.org/10.1002/9781118628522.ch11

Unsupervised Decomposition Methods for Analysis of Multimodal Neural Data. / Biessmann, Felix; Meinecke, Frank C.; Muller, Klaus.

Introduction to Neural Engineering for Motor Rehabilitation. wiley, 2013. p. 199-234.

Research output: Chapter in Book/Report/Conference proceedingChapter

Biessmann, F, Meinecke, FC & Muller, K 2013, Unsupervised Decomposition Methods for Analysis of Multimodal Neural Data. in Introduction to Neural Engineering for Motor Rehabilitation. wiley, pp. 199-234. https://doi.org/10.1002/9781118628522.ch11
Biessmann F, Meinecke FC, Muller K. Unsupervised Decomposition Methods for Analysis of Multimodal Neural Data. In Introduction to Neural Engineering for Motor Rehabilitation. wiley. 2013. p. 199-234 https://doi.org/10.1002/9781118628522.ch11
Biessmann, Felix ; Meinecke, Frank C. ; Muller, Klaus. / Unsupervised Decomposition Methods for Analysis of Multimodal Neural Data. Introduction to Neural Engineering for Motor Rehabilitation. wiley, 2013. pp. 199-234
@inbook{fd0e58c3cd344ce888a53546d47c7c37,
title = "Unsupervised Decomposition Methods for Analysis of Multimodal Neural Data",
abstract = "Technical advances in the field of noninvasive neuroimaging allow for innovative therapeutical strategies with application potential in neural rehabilitation. To improve these methods, combinations of multiple imaging modalities have become an important topic of research. This chapter reviews some of the most popular unsupervised statistical learning techniques used in the context of neuroscientific data analysis, and places a special focus on multimodal neural data. It starts with the well-known principal component analysis (PCA). First, the chapter shows how to derive the algorithm and provides illustrative examples of the advantages and disadvantages of standard PCA. The second method presented is canonical correlation analysis (CCA): a multivariate analysis method that reveals maximally correlated features of simultaneously acquired multiple data streams. Finally the chapter presents a straightforward extension of CCA that estimates the correct solution even in the presence of noninstantaneous couplings, that is, temporal delays or convolutions between data sources.",
keywords = "Canonical correlation analysis (CCA), Multimodal neural data, Noninvasive neuroimaging, Principal component analysis (PCA)",
author = "Felix Biessmann and Meinecke, {Frank C.} and Klaus Muller",
year = "2013",
month = "7",
day = "15",
doi = "10.1002/9781118628522.ch11",
language = "English",
isbn = "9780470916735",
pages = "199--234",
booktitle = "Introduction to Neural Engineering for Motor Rehabilitation",
publisher = "wiley",

}

TY - CHAP

T1 - Unsupervised Decomposition Methods for Analysis of Multimodal Neural Data

AU - Biessmann, Felix

AU - Meinecke, Frank C.

AU - Muller, Klaus

PY - 2013/7/15

Y1 - 2013/7/15

N2 - Technical advances in the field of noninvasive neuroimaging allow for innovative therapeutical strategies with application potential in neural rehabilitation. To improve these methods, combinations of multiple imaging modalities have become an important topic of research. This chapter reviews some of the most popular unsupervised statistical learning techniques used in the context of neuroscientific data analysis, and places a special focus on multimodal neural data. It starts with the well-known principal component analysis (PCA). First, the chapter shows how to derive the algorithm and provides illustrative examples of the advantages and disadvantages of standard PCA. The second method presented is canonical correlation analysis (CCA): a multivariate analysis method that reveals maximally correlated features of simultaneously acquired multiple data streams. Finally the chapter presents a straightforward extension of CCA that estimates the correct solution even in the presence of noninstantaneous couplings, that is, temporal delays or convolutions between data sources.

AB - Technical advances in the field of noninvasive neuroimaging allow for innovative therapeutical strategies with application potential in neural rehabilitation. To improve these methods, combinations of multiple imaging modalities have become an important topic of research. This chapter reviews some of the most popular unsupervised statistical learning techniques used in the context of neuroscientific data analysis, and places a special focus on multimodal neural data. It starts with the well-known principal component analysis (PCA). First, the chapter shows how to derive the algorithm and provides illustrative examples of the advantages and disadvantages of standard PCA. The second method presented is canonical correlation analysis (CCA): a multivariate analysis method that reveals maximally correlated features of simultaneously acquired multiple data streams. Finally the chapter presents a straightforward extension of CCA that estimates the correct solution even in the presence of noninstantaneous couplings, that is, temporal delays or convolutions between data sources.

KW - Canonical correlation analysis (CCA)

KW - Multimodal neural data

KW - Noninvasive neuroimaging

KW - Principal component analysis (PCA)

UR - http://www.scopus.com/inward/record.url?scp=85017445716&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85017445716&partnerID=8YFLogxK

U2 - 10.1002/9781118628522.ch11

DO - 10.1002/9781118628522.ch11

M3 - Chapter

SN - 9780470916735

SP - 199

EP - 234

BT - Introduction to Neural Engineering for Motor Rehabilitation

PB - wiley

ER -